Next Meetup

AI in Production:Compressing Deep Learning Models for IoT
Abstract: Deep learning is the force behind some of the recent notable technological advancements and also fake news around AI. Although useful it can be expensive computationally. This in turns limits its usefulness when there not enough compute resources (IoT) or when it is simply too expensive to use (cloud is not free). In this talk, we review what deep learning is from a point of view which facilitates the rest of the discussion. Then we look at some practical ways of shrinking model sizes. We particularly are interested in methods that can result in a reduction on the order of 4x-100x. Speaker : Alireza Kenarsari Alireza is the founder of Picovoice ( - a Canadian AI startup building voice-enabled AI technology that can be embedded into any product. Prior to Picovoice Alireza was a Senior Engineer at Amazon and has been also an early-stage engineer in a few successful technology startups. He is the inventor of five US patents within the fields of deep learning and speech recognition. Agenda: 5:00pm - Doors Open 5:30pm - Talk starts 6:00pm - Building doors lock 6:30pm - Questions, start-wrapping up 7:00pm - We're back on the streets and heading somewhere hopefully. Entry to the building shuts at 6pm! (Did I say that already?). In case you have trouble getting in before 6pm, text[masked] (Aanchan Mohan) or email me at [masked]. We're also on vantech slack at on the #productionml channel.

WeWork Burrard Station

16th floor - 595 Burrard · Vancouver, BC

What we're about

Welcome to the Data Science LEARNING Group!

A meetup for people who want to LEARN Data Science as a group. Taking online courses together. Reading books together. Etc. Also with some hands-on workshops taught by 'experts'. It's also a place where you can ask others questions and for help.

This is a sister meetup of: (That's where talks are held.)

But we're at:

Also, join us on the VanTech slack! Join VanTech here:

And then join the Data Science channel here:

What you want to learn not listed here? If you would like a new learning group (on a topic for which there is no learning group yet), please contact the organizers.

Members (3,314)

Photos (84)

Find us also at